© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63354
    Prev
    Next
    INDEX
    Explanations

    increasing demand or usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagon
    -0.09
    å·¥ä½ľæĸ¹æ¡Ī
    -0.09
    ä¸įæŃ»
    -0.08
    æīįç®Ĺ
    -0.08
    æŃ¤æ¬¡
    -0.08
    ãģIJ
    -0.08
    Nullable
    -0.08
     señ
    -0.08
    è°ĭåĪĴ
    -0.08
    è¿ĺåı¯ä»¥
    -0.08
    POSITIVE LOGITS
    è¶ĬæĿ¥è¶Ĭ
    0.16
    è¶ĬæĿ¥è¶Ĭé«ĺ
    0.16
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.15
    è¶ĬæĿ¥
    0.13
    è¶Ĭä¾Ĩè¶Ĭ
    0.13
    è¶Ĭä¾Ĩ
    0.12
     increasingly
    0.12
    é«ĺ涨
    0.11
    è¦ģæ±Ĥ
    0.11
    ãģĮå¢ĹãģĪ
    0.10
    Activations Density 0.748%

    No Known Activations